Max Robotics — Global Service Robot Directory + US Certification

About

Shengjie Qiu is a pioneering researcher at the intersection of tactile sensing, multimodal fusion, and robotic manipulation. His work centers on developing intelligent systems that integrate tactile, visual, and textual information to enhance object recognition and robotic interaction. Qiu’s major contributions include the TVT-Transformer, a novel tactile-visual-textual fusion network that achieves superior object recognition performance by leveraging the complementary strengths of multiple sensory modalities—a breakthrough that has already garnered 20 citations since its 2025 publication. His earlier DT-Transformer model pioneered text-tactile fusion, addressing the scalability limitations of visual-haptic methods by using textual descriptions to overcome dataset constraints. Qiu has also advanced tactile-based object recognition by fusing shape and texture attributes through data augmentation and attention mechanisms, significantly improving classification accuracy for objects with similar features. Beyond perception, his work on reinforcement learning for prosthetic control and dexterous grasping demonstrates a commitment to real-world applications, including interactive algorithms for shoulder-amputated prostheses and push-grasp policies for multi-finger hands. With a rapidly growing citation impact and a focus on bridging sensory gaps in robotics, Qiu is shaping the future of multimodal AI and assistive technologies.